The hippocampus plays a crucial role in memory and cognition. Because of the associated toxicity from whole brain radiotherapy, more advanced treatment planning techniques prioritize hippocampal avoidance, which depends on an accurate segmentation of the small and complexly shaped hippocampus. To achieve accurate segmentation of the anterior and posterior regions of the hippocampus from T1 weighted (T1w) MR images, we developed a novel model, Hippo-Net, which uses a cascaded model strategy. The proposed model consists of two major parts: (1) a localization model is used to detect the volume-of-interest (VOI) of hippocampus. (2) An end-to-end morphological vision transformer network (Franchi et al 2020 Pattern Recognit. 102 107246, Ranem et al 2022 IEEE/CVF Conf. on Computer Vision and Pattern Recognition Workshops (CVPRW) pp 3710–3719) is used to perform substructures segmentation within the hippocampus VOI. The substructures include the anterior and posterior regions of the hippocampus, which are defined as the hippocampus proper and parts of the subiculum. The vision transformer incorporates the dominant features extracted from MR images, which are further improved by learning-based morphological operators. The integration of these morphological operators into the vision transformer increases the accuracy and ability to separate hippocampus structure into its two distinct substructures. A total of 260 T1w MRI datasets from medical segmentation decathlon dataset were used in this study. We conducted a five-fold cross-validation on the first 200 T1w MR images and then performed a hold-out test on the remaining 60 T1w MR images with the model trained on the first 200 images. In five-fold cross-validation, the Dice similarity coefficients were 0.900 ± 0.029 and 0.886 ± 0.031 for the hippocampus proper and parts of the subiculum, respectively. The mean surface distances (MSDs) were 0.426 ± 0.115 mm and 0.401 ± 0.100 mm for the hippocampus proper and parts of the subiculum, respectively. The proposed method showed great promise in automatically delineating hippocampus substructures on T1w MR images. It may facilitate the current clinical workflow and reduce the physicians’ effort.

Introduction: Neutrophil-to-lymphocyte ratio (NLR) is a surrogate for systemic inflammatory response and its elevation has been shown to be a poor prognostic factor in various malignancies. Stereotactic radiosurgery (SRS) can induce a leukocyte-predominant inflammatory response. This study investigates the prognostic impact of post-SRS NLR in patients with brain metastases (BM). Methods: BM patients treated with SRS from 2003 to 2015 were retrospectively identified. NLR was calculated from the most recent full blood counts post-SRS. Overall survival (OS) and intracranial outcomes were calculated using the Kaplan–Meier method and cumulative incidence with competing risk for death, respectively. Results: 188 patients with 328 BM treated with SRS had calculable post-treatment NLR values. Of these, 51 (27.1%) had a NLR > 6. The overall median imaging follow-up was 13.2 (14.0 vs. 8.7 for NLR ≤ 6.0 vs. > 6.0) months. Baseline patient and treatment characteristics were well balanced, except for lower rate of ECOG performance status 0 in the NLR > 6 cohort (33.3 vs. 44.2%, p = 0.026). NLR > 6 was associated with worse 1- and 2-year OS: 59.9 vs. 72.9% and 24.6 vs. 43.8%, (p = 0.028). On multivariable analysis, NLR > 6 (HR: 1.53; 95% CI 1.03–2.26, p = 0.036) and presence of extracranial metastases (HR: 1.90; 95% CI 1.30–2.78; p < 0.001) were significant predictors for worse OS. No association was seen with NLR and intracranial outcomes. Conclusion: Post-treatment NLR, a potential marker for post-SRS inflammatory response, is inversely associated with OS in patients with BM. If prospectively validated, NLR is a simple, systemic marker that can be easily used to guide subsequent management.

Background: The purpose of this study was to evaluate predictors of early distant brain failure (DBF) and salvage whole brain radiotherapy (WBRT) after treatment with stereotactic radiosurgery (SRS) for brain metastases and create a clinically relevant risk score in order to stratify patients’ risk of these events. Methods: We reviewed records of 270 patients with brain metastases treated with SRS between 2003-2012. Pre-treatment patient and tumor characteristics were analyzed by univariate and multivariable analyses. Cumulative incidence (CI) of first DBF and salvage WBRT were calculated. Significant factors were used to create a score for stratifying early (6-month) DBF risk. Results: No prior WBRT, total lesion volume <1.3 cm3, primary breast cancer or malignant melanoma histology, and multiple metastases (≥2) were found to be significant predictors for early DBF. Each factor was ascribed one point due to similar hazard ratios. Scores of 0-1, 2, and 3-4 were considered low, intermediate, and high risk, respectively. This correlated with 6-month CI of DBF of 16.6%, 28.8%, and 54.4%, respectively (p<0.001). For patients without prior WBRT, the 6-month CI of salvage WBRT by 6-months was 2%, 17.7%, and 25.7%, respectively (p<0.001). Conclusion: Early DBF after SRS requiring salvage WBRT remains a significant clinical problem. Patient stratification for early DBF can better inform the decision for initial treatment strategy for brain metastases. The provided risk score may help predict for early DBF and subsequent salvage WBRT if initial SRS is used. External validation is needed prior to clinical implementation.

We develop a learning-based method to generate patient-specific pseudo computed tomography (CT) from routinely acquired magnetic resonance imaging (MRI) for potential MRI-based radiotherapy treatment planning. The proposed pseudo CT (PCT) synthesis method consists of a training stage and a synthesizing stage. During the training stage, patch-based features are extracted from MRIs. Using a feature selection, the most informative features are identified as an anatomical signature to train a sequence of alternating random forests based on an iterative refinement model. During the synthesizing stage, we feed the anatomical signatures extracted from an MRI into the sequence of well-trained forests for a PCT synthesis. Our PCT was compared with original CT (ground truth) to quantitatively assess the synthesis accuracy. The mean absolute error, peak signal-to-noise ratio, and normalized cross-correlation indices were 60.87 ± 15.10 HU, 24.63 ± 1.73 dB, and 0.954 ± 0.013 for 14 patients' brain data and 29.86 ± 10.4 HU, 34.18 ± 3.31 dB, and 0.980 ± 0.025 for 12 patients' pelvic data, respectively. We have investigated a learning-based approach to synthesize CTs from routine MRIs and demonstrated its feasibility and reliability. The proposed PCT synthesis technique can be a useful tool for MRI-based radiation treatment planning.

Magnetic resonance imaging (MRI) provides a number of advantages over computed tomography (CT) for radiation therapy treatment planning; however, MRI lacks the key electron density information necessary for accurate dose calculation. We propose a dictionary-learning-based method to derive electron density information from MRIs. Specifically, we first partition a given MR image into a set of patches, for which we used a joint dictionary learning method to directly predict a CT patch as a structured output. Then a feature selection method is used to ensure prediction robustness. Finally, we combine all the predicted CT patches to obtain the final prediction for the given MR image. This prediction technique was validated for a clinical application using 14 patients with brain MR and CT images. The peak signal-to-noise ratio (PSNR), mean absolute error (MAE), normalized cross-correlation (NCC) indices and similarity index (SI) for air, soft-tissue and bone region were used to quantify the prediction accuracy. The mean ± std of PSNR, MAE, and NCC were: 22.4±1.9dB, 82.6±26.1 HU, and 0.91±0.03 for the 14 patients. The SIs for air, soft-tissue, and bone regions are 0.98±0.01, 0.88±0.03, and 0.69±0.08. These indices demonstrate the CT prediction accuracy of the proposed learning-based method. This CT image prediction technique could be used as a tool for MRI-based radiation treatment planning, or for PET attenuation correction in a PET/MRI scanner.

Purpose: Glioblastoma (GBM) neurosurgical resection relies on contrast-enhanced MRI-based neuronavigation. However, it is well-known that infiltrating tumor extends beyond contrast enhancement. Fluorescence-guided surgery (FGS) using 5-aminolevulinic acid (5-ALA) was evaluated to improve extent of resection (EOR) of GBMs. Preoperative morphological tumor metrics were also assessed. Procedures: Thirty patients from a phase II trial evaluating 5-ALA FGS in newly diagnosed GBM were assessed. Tumors were segmented preoperatively to assess morphological features as well as postoperatively to evaluate EOR and residual tumor volume (RTV). Results: Median EOR and RTV were 94.3 % and 0.821 cm3, respectively. Preoperative surface area to volume ratio and RTV were significantly associated with overall survival, even when controlling for the known survival confounders. Conclusions: This study supports claims that 5-ALA FGS is helpful at decreasing tumor burden and prolonging survival in GBM. Moreover, morphological indices are shown to impact both resection and patient survival.

In brain tumor patients, worsening of imaging findings in the first 6 months after surgical debulking and chemoradiation can occur in the absence of tumor growth, a phenomenon known as pseudoprogression. Awareness of pseudoprogression is important as it can lead to unnecessary additional changes in patient management. In this case, a patient with bilateral frontal glioblastoma presented with new post-treatment brainstem leptomeningeal enhancement which was distant from the original tumor site, concerning for disease progression. However, the patient was asymptomatic and correlation of leptomeningeal enhancement locations with radiation therapy dose maps revealed high doses at the affected site, supporting a diagnosis of treatment effect which was confirmed by resolution on follow-up imaging after treatment with steroids. Parenchymal pseudoprogression in brain tumor patients is well-documented, but worsening leptomeningeal enhancement following therapy may also represent treatment effects. If spatially remote leptomeningeal enhancement occurs, correlation with radiation dose maps may be useful in suggesting a diagnosis of treatment effect over tumor progression.

Glioblastoma is a common and aggressive form of brain cancer affecting up to 20,000 new patients in the US annually. Despite rigorous therapies, current median survival is only 15–20 months. Patients who complete initial treatment undergo follow-up imaging at routine intervals to assess for tumor recurrence. Imaging is a central part of brain tumor management, but MRI findings in patients with brain tumor can be challenging to interpret and are further confounded by interpretation variability. Disease-specific structured reporting attempts to reduce variability in imaging results by implementing well-defined imaging criteria and standardized language. The Brain Tumor Reporting and Data System (BT-RADS) is one such framework streamlined for clinical workflows and includes quantitative criteria for more objective evaluation of follow-up imaging. To facilitate accurate and objective monitoring of patients during the follow-up period, we developed a cloud platform, the Brain Imaging Collaborative Suite’s Longitudinal Imaging Tracker (BrICS-LIT). BrICS-LIT uses semiautomated tumor segmentation algorithms of both T2-weighted FLAIR and contrast-enhanced T1-weighted MRI to assist clinicians in quantitative assessment of brain tumors. The LIT platform can ultimately guide clinical de-cision-making for patients with glioblastoma by providing quantitative metrics for BT-RADS scoring. Further, this platform has the potential to increase objectivity when measuring efficacy of novel therapies for patients with brain tumor during their follow-up. Therefore, LIT will be used to track patients in a dose-escalated clinical trial, where spectroscopic MRI has been used to guide radiation therapy (Clinicaltrials.gov NCT03137888), and compare patients to a control group that received standard of care.

Objective: Both stereotactic radiosurgery (SRS) and fractionated radiation therapy (FRT) techniques are used for treatment of intracranial meningiomas with excellent local control (LC) rates. Although SRS techniques are convenient, toxicity including treatment-related edema can significantly impact patient quality of life. The long-term clinical outcomes of patients with magnetic resonance imaging (MRI)–defined meningiomas treated with radiation therapy (RT) alone are reported. Methods: The charts of 211 patients with meningiomas diagnosed by contrast-enhanced MRI treated with either SRS or FRT between 1991 and 2012 at a single institution were reviewed. Actuarial rates for LC and development of treatment-related radiographic edema (TRE) were determined by the Kaplan-Meier method. Results: There were 211 patients who received radiation therapy for 223 lesions. Median follow-up was 5.7 years. Eleven patients experienced a local failure; of these, 2 were ultimately found to have pathologically proven metastatic carcinoma. Two- and 5-year LC was 97.8% and 94.6%, respectively, with no significant difference based on modality of therapy. Actuarial rate for development of TRE at 1 and 2 years was 30.1% and 34.6% for the SRS group and 1.6% and 2.5% for the FRT group, respectively (P < 0.001). Conclusions: RT alone using a limited margin is an effective treatment option for MRI-defined meningiomas and should be considered even without biopsy if surgery will present significant morbidity. Although LC with SRS versus FRT was comparable, FRT was associated with a significantly decreased risk of TRE.

Histone deacetylases regulate a wide variety of cellular functions and have been implicated in redifferentiation of various tumors. Histone deacetylase inhibitors (HDACi) are potential pharmacologic agents to improve outcomes for patients with gliomas. We assessed the therapeutic efficacy of belinostat (PXD-101), an HDACi with blood-brain barrier permeability. Belinostat was first tested in an orthotopic rat glioma model to assess in vivo tumoricidal effect. Our results showed that belinostat was effective in reducing tumor volume in the orthotopic rat glioma model in a dose-dependent manner. We also tested the antidepression activity of belinostat in 2 animal models of depression and found it to be effective. Furthermore, we confirmed that myo-inositol levels improved by belinostat treatment in vitro. In a human pilot study, it was observed that belinostat in combination with chemoradiation may delay initial recurrence of disease. Excitingly, belinostat significantly improved depressive symptoms in patients with glioblastoma compared with control subjects. Finally, spectroscopic magnetic resonance imaging of 2 patient cases from this pilot study are presented to indicate how spectroscopic magnetic resonance imaging can be used to monitor metabolite response and assess treatment effect on whole brain. This study highlights the potential of belinostat to be a synergistic therapeutic agent in the treatment of gliomas.